I am trying to understand SAM module (version shown on YOLOv4 paper).
def sam(x):
# If channels last
n_c = K.int_shape(x)[-1]
# 3x3 filter version
h = Conv2D(kernel_size=3, filters=n_c, strides=1, padding='same')(x)
# 1x1 filter version (should include only channel information)
# h = Conv2D(kernel_size=1, filters=n_c, strides=1, padding='same')(x)
# h = BatchNormalization()(h)
gate = Activation(sigmoid)(h)
return Multiply()([x,gate])
My question:
Is batch norm. used
Is this what was presented in the paper?
Note: 1x1 conv. probably doesn't make sense, since it isn't taking spatial info. (was just testing)
I am trying to understand SAM module (version shown on YOLOv4 paper).
My question:
Note: 1x1 conv. probably doesn't make sense, since it isn't taking spatial info. (was just testing)